mcpField
W
web-search

web-search

github.com/ogulcancelikProductivity80253 installsUpdated 6d ago
Repository

About web-search

web-search is a CLI skill for agents to search the web, fetch pages, and turn them into clean Markdown context. Its persistent local browser daemon keeps a warm session between calls.

Key features

  1. 01Search the web through a local browser
  2. 02Fetch selected search results
  3. 03Extract pages as clean Markdown
  4. 04Manage a persistent browser daemon

Use cases

  1. 01Gather web sources for an agent response
  2. 02Fetch selected pages from a search
  3. 03Extract full page text when needed

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ogulcancelik/agent-skills --skill web-search

After installing, type/web-searchin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

.gitignore
LICENSE
package.json
README.md
web-search.js
lib/
bot-protection.js
browser-bin.js
cdp.js
daemon-client.js
daemon.js
debug-dump.js
extract.js
fetch.js
fingerprint.js
http-fetch.js
search-cache.js
search.js
test/
bot-protection.test.js
browser-bin.test.js
daemon-client.test.js
extract.test.js
fingerprint.test.js
search-cache.test.js
search-ddg.test.js
search-google.test.js

Details

From the project README

Web Search

Use the bundled CLI to search through a local browser, visit results, and extract pages as clean Markdown for agent context. The persistent browser daemon reduces bot-detection failures and avoids repeated browser startup costs.

The entry point is {baseDir}/web-search.js, where {baseDir} is the absolute directory containing this SKILL.md. Always invoke that absolute path. Never run ./web-search.js from the caller's project directory.

Setup

If dependencies are missing, run bun install in the skill directory.

The CLI auto-detects Chromium-family browsers. Override detection with WEB_SEARCH_BROWSER_BIN or --browser-bin <path>.

Search and fetch

{baseDir}/web-search.js "query"
{baseDir}/web-search.js "query" -n 10
{baseDir}/web-search.js --from <result-set-id> --fetch 1,3,5
{baseDir}/web-search.js --url https://example.com
{baseDir}/web-search.js --url https://example.com --full

Each search prints a result-set ID. Always pass that ID with --from when fetching numbered results; result sets expire after ten minutes. Use --full only when the complete page text is needed.

Browser daemon

Direct calls use a local daemon by default for a warm browser session.

{baseDir}/web-search.js --daemon status
{baseDir}/web-search.js --daemon start
{baseDir}/web-search.js --daemon stop
{baseDir}/web-search.js --daemon restart
{baseDir}/web-search.js --no-daemon --url https://example.com

Troubleshooting

Treat one blocked page as a normal site-specific failure. Retry once, use another result, or try the direct URL before changing browser state.

For repeated timeouts, daemon errors, or blocks across multiple attempts:

  1. Check {baseDir}/web-search.js --daemon status.
  2. Run {baseDir}/web-search.js --daemon restart and retry.
  3. If blocks persist, inspect health.profileDir in the status output. Stop the daemon, delete only that hidden skill profile directory, then start the daemon again. This resets stale cookies and browser storage without touching the user's normal browser profile.

Never clear the profile after a single block. Profile reset is a last resort for persistent failures.

Reporting

Use the URLs actually searched or fetched as sources. Cite those URLs when answering from web material.

Comments

Markdown supported